Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to rumors and speculative statements, particularly concerning celebrities or high-profile individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TimeUnit
    -0.80
    GraphicsUnit
    -0.78
    Diweddarwch
    -0.77
    ########.
    -0.75
     WaitForSeconds
    -0.74
    httphttps
    -0.74
    </tfoot>
    -0.71
    DotNetBar
    -0.68
    ChildIndex
    -0.68
     prestazioni
    -0.68
    POSITIVE LOGITS
     rumour
    0.74
     rumor
    0.65
     rumours
    0.60
    rum
    0.58
     rumors
    0.57
     leaked
    0.55
     Rum
    0.52
     gossip
    0.51
     Rumors
    0.50
     RUM
    0.47
    Act Density 0.112%

    No Known Activations